Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add meltedinhex/analyst-ai-pack --skill writing-yara-rules-from-reversed-codegit clone --depth 1 https://github.com/meltedinhex/analyst-ai-packWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/writing-yara-rules-from-reversed-code)<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/writing-yara-rules-from-reversed-code"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/writing-yara-rules-from-reversed-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/writing-yara-rules-from-reversed-code"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/writing-yara-rules-from-reversed-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.00839 |
| Opus 5 | $0.00038 | $0.00419 |
| Sonnet 5 | $0.00015 | $0.00168 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
writing-yara-rules-from-reversed-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing YARA Rules from Reversed Code
When to Use
- You finished reversing a sample/family and want a detection that survives recompilation and cosmetic changes.
- You need byte-pattern signatures from decryptors, API-hash constants, or unique algorithms rather than fragile strings.
- You are converting RE notes into hunting/scanning rules for a corpus.
Do not use volatile artifacts (file paths, mutex names that change per build, packer stubs shared across unrelated families) as your primary anchor — they cause drift and false hits.
Prerequisites
- The
yaraengine (and ideallyyara-python) for testing. - A small corpus: target samples (true positives) and clean/unrelated files (false-positive control).
Workflow
Step 1: Choose stable anchors
Prefer, in order: a unique algorithm's opcode sequence (decryptor, hashing loop), embedded magic constants (API hashes, XOR keys, S-box), then distinctive strings only if intrinsic.
Step 2: Extract byte patterns with wildcards
Pull the relevant opcodes and wildcard volatile operands (addresses, immediates) so the rule survives relocation/recompilation:
$dec = { 8A 04 ?? 34 ?? 88 04 ?? 41 3B ?? 7? ?? } ; xor-decrypt loop, regs/disp wildcarded
Step 3: Assemble the rule
Combine 2–3 independent anchors with a condition requiring enough of them, plus a cheap
prefilter (file size, PE magic) to keep scanning fast:
python scripts/analyst.py scaffold --name family_xyz --hash 0xABCDEF12
Step 4: Validate against the corpus
Run the rule across true positives and the clean control set; require all TPs match and zero FPs on the control.
yara -r rules/family_xyz.yar ./corpus
Step 5: Tune and document
Adjust thresholds, add meta (author, date, reference, hash), and record which construct each
string anchors so future analysts can maintain it.
Validation
- Rule matches all intended samples and produces zero hits on the clean control set.
- Anchors map to intrinsic code/constants, not build-specific noise.
metadocuments source samples and the reasoning for each pattern.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 104 lines · 76 tokens per session scan A 6a0eff30cf64
writing-yara-rules-from-reversed-code is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 839 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
yara-rule-writing-malware
Write custom YARA rules to identify and classify malware based on textual and binary patterns. This skill focuses on creating robust signatures using strings, regular expressions, and hexadecimal opcodes extracted during malware analysis for enterprise threat hunting.
detection-sigma
Generic detection rule creation and management using Sigma, the universal SIEM rule format. Sigma provides vendor-agnostic detection logic for log analysis across multiple SIEM platforms. Use when: (1) Creating detection rules for security monitoring, (2) Converting rules between SIEM platforms (Splunk, Elastic…
analyzing-cobalt-strike-beacon-configuration
Extract and analyze Cobalt Strike beacon configuration from PE files and memory dumps to identify C2 infrastructure, malleable profiles, and operator tradecraft.
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…
Threat Hunting & IOC Analysis
IOC extraction, threat intelligence correlation, MITRE ATT&CK mapping, hunt hypothesis generation, and detection rule creation.